Trans. Assoc. Comput. Linguistics 2021
89 papers
In 2021, Transactions of the Association for Computational Linguistics (TACL) published 112 papers, with a strong emphasis on the reliability and evaluation of text summarization. Research themes focused on factual faithfulness, the trade-off between faithfulness and abstractiveness, and methods for summarizing without human annotations. Other prominent areas of investigation included balanced data sampling for multi-task learning and the dynamics of multimodal fusion mechanisms.
The year’s output also highlighted advancements in multilingualism and model robustness. Key contributions included the MKQA benchmark for multilingual open-domain question answering and analyses of how morphology affects language modeling. Technical developments featured model compression via causal effect estimation, decontextualization techniques to make sentences stand-alone, and edit-based transformers for machine translation. Prolific authors contributing to these developments included Graham Neubig, Yoav Goldberg, and Mirella Lapata. Collectively, the research reflected an interest in improving systematic generalization and the semantic compatibility of language models across diverse linguistic contexts.
Top Research Directions
Research directions most represented by Trans. Assoc. Comput. Linguistics 2021 papers.
Top Authors
Impactful Papers
Papers from Trans. Assoc. Comput. Linguistics 2021 that shaped research clusters.
Influential
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answer
influential
Factual Inaccuracy and Hallucination in
MasakhaNER: Named Entity Recognition for African Languages
influential
Mitigating Data Scarcity in Low Resource
MasakhaNER: Named Entity Recognition for African Languages
influential
Mitigating Data Scarcity in Low Resource
MasakhaNER: Named Entity Recognition for African Languages
influential
Adapting Natural Language Processing to
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
influential
Inductive Graph Embeddings for Dynamic N
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjec
influential
Harmonizing Syntax with Universal Depend
Neural Modeling for Named Entities and Morphology (NEMO2)
influential
Overcoming Cascading Errors from Automat
What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and
influential
Restoring Structure and Punctuation in S
Planning with Learned Entity Prompts for Abstractive Summarization
influential
The Upstream Entity Recognition Bottlene
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answer
influential
Post-Hoc Logit Scaling for Probability C
Papers
« prev Page 2/2